Skip to content
VLA 線 · 查看同日 AI 報告 →查看同日 AI 报告 →
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —

VLA 研究日報VLA 研究日报

共 35 篇

⚡ 突破

🔧 技術技术

VLA [Stanford University]

Q-Learning With World Models

Perry Dong et al. · 结合世界模型进行离线Q-learning,提升VLA模型的RL精调样本效率。提供了将世界模型预测融入价值学习的清晰路径,可直接应用于现有VLA框架的后训练阶段。

📖 背景閱讀背景阅读

VLA [National Institute of Advanced Industrial Science and Technology (AIST)]

The Embodiment Gap in Robot Foundation Models

Yukiyasu Domae et al. · 探讨机器人基础模型中的'具身差距'问题,指出单纯扩展数据/模型未必能解决泛化。属于理论分析或观点类文章,未提出具体可复用的新VLA架构或训练方法。

VLA [IIIS, Tsinghua University]

ORV: 4D Occupancy-centric Robot Video Generation

Xiuyu Yang et al. · 提出基于4D占据中心的机器人视频生成方法,旨在解决数据稀缺。属于世界模型/数据生成方向,虽重要但当前版本可能更侧重生成质量而非控制闭环的直接集成。

VLA [Zhejiang University]

WONDER: A Radio World Model-based Negotiation Framework for Multi-Agent UAV Coverage Optimization

Jiahao Huang et al. · arXiv:2608.16955v1 Announce Type: cross Abstract: Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (UAV) swarms provide a promising solution for rapid restoration.However, due to the limitations in local geometry observations hidden radio impact,and inter-UAV communication,there exists a significant gap between locally visible movement choices and swarm-level coverage outcomes.To combat this gap,we propose a raido World-model-based Op

VLA [Shenyang Pharmaceutical University]

Towards Zero-Shot Task Transfer with Neurosymbolic World Models

Isidoro Tamassia et al. · arXiv:2608.17959v1 Announce Type: cross Abstract: State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these models are generally task-dependent: they learn uninterpretable latent representations that are tied to the training task and thus hard to generalize to new tasks. In this work, we present a novel world model fo